Blind zone prediction for PCA-based sensor fault detection

doi:10.11949/j.issn.0438-1157.20161488

Abstract

Abstract:

Sensor faults occur unavoidably but cannot be detected easily. Sensor measurement is fundamental for safe operation and optimal energy conservation of refrigeration and air-conditioning systems. After analyzed procedure for sensor fault detection based on the principal component analysis (PCA) with Q-statistics as fault detection boundary, blind zone prediction was established as an index to estimate sensor fault detectability. The index was used to assess fault detectability of each sensor in training dataset and to analyze, evaluate, and optimize dataset quality of training model. Results of analyzing in-site and laboratory datasets of water-cooled chillers at different introduced fault levels show that the blind zone can effectively predict fault detection outcome for sensors by selected datasets.

Key words: sensor, fault detection blind zone, principal component analysis, parameter estimation, algorithm

摘要：

传感器故障极易发生但不易察觉，其测量数据是制冷空调系统安全运行和优化节能的必要条件。分析了以Q统计量为故障检测边界的基于主元分析的传感器故障检测流程，建立了一种预测传感器故障检测能力的指标——故障检测盲区，用于预测训练数据集中各个传感器的故障检测能力，从而分析、评价和优化建模用训练数据的质量。采用工程数据、实验数据分别开展算法验证，结果表明故障检测盲区能有效预测选定数据集的相关传感器的故障检测结果。

关键词: 传感器, 故障检测盲区, 主元分析, 参数估值, 算法

CLC Number:

TB65

HU Yunpeng. Blind zone prediction for PCA-based sensor fault detection[J]. CIESC Journal, 2017, 68(4): 1509-1515.

胡云鹏. 基于主元分析的传感器故障检测盲区预测[J]. 化工学报, 2017, 68(4): 1509-1515.

References 31

[1]	LEE S H, YIK F W H. A study on the energy penalty of various air-side system faults in buildings[J]. Energy and Buildings, 2010, 42(1):2-10.
[2]	GINESTET S, MARCHIO D, MORISOT O. Evaluation of faults impacts on energy consumption and indoor air quality on an air handling unit[J]. Energy and Buildings, 2008, 40(1):51-57.
[3]	YU Y, WORADECHJUMROEN D, YU D. A review of fault detection and diagnosis methodologies on air-handling units[J]. Energy and Buildings, 2014, 82:550-562.
[4]	PIACENTINO A, TALAMO M. Innovative thermoeconomic diagnosis of multiple faults in air conditioning units:methodological improvements and increased reliability of results[J]. International Journal of Refrigeration, 2013, 36(8):2343-2365.
[5]	PIACENTINO A, TALAMO M. Critical analysis of conventional thermoeconomic approaches to the diagnosis of multiple faults in air conditioning units:capabilities, drawbacks and improvement directions. A case study for an air-cooled system with 120 kW capacity[J]. International Journal of Refrigeration, 2013, 36(1):24-44.
[6]	KIM W, AUN J E. Development and evaluation of virtual refrigerant mass flow sensors for fault detection and diagnostics[J]. International Journal of Refrigeration, 2016, 63:184-198.
[7]	WANG S W, XIAO F. AHU sensor fault diagnosis using principal component analysis method[J]. Energy and Buildings, 2004, 36(2):147-160.
[8]	CHEN Y M, LAN L L. Fault detection, diagnosis and data recovery for a real building heating/cooling billing system[J]. Energy Conversion and Management, 2010, 51(5):1015-1024.
[9]	HU Y P, CHEN H X, LI G N, et al. A statistical training data cleaning strategy for the PCA-based chiller sensor fault detection, diagnosis and data reconstruction method[J]. Energy and Buildings, 2016, 112:270-278.
[10]	PADILLA M, CHOINIÈRE D. A combined passive-active sensor fault detection and isolation approach for air handling units[J]. Energy and Buildings, 2015, 99:214-219.
[11]	HU Y P, LI G X, CHEN H X, et al. Sensitivity analysis for PCA-based chiller sensor fault detection[J]. International Journal of Refrigeration, 2016, 63:133-143.
[12]	KIM M, LIU H, KIM J T, et al. Sensor fault identification and reconstruction of indoor air quality (IAQ) data using a multivariate non-Gaussian model in underground building space[J]. Energy and Buildings, 2013, 66:384-394.
[13]	DU Z M, FAN B, CHI J L, et al. Sensor fault detection and its efficiency analysis in air handling unit using the combined neural networks[J]. Energy and Buildings, 2014, 72:157-166.
[14]	KOCYIGIT N. Fault and sensor error diagnostic strategies for a vapor compression refrigeration system by using fuzzy inference systems and artificial neural network[J]. International Journal of Refrigeration, 2015, 50:69-79.
[15]	LIANG J, DU R. Model-based fault detection and diagnosis of HVAC systems using support vector machine method[J]. International Journal of Refrigeration, 2007, 30(6):1104-1114.
[16]	YANG X B, JIN X Q, DU Z M, et al. Optimum operating performance based online fault-tolerant control strategy for sensor faults in air conditioning systems[J]. Automation in Construction, 2014, 37:145-154.
[17]	李冠男, 胡云鹏, 陈焕新, 等. 基于SVDD的冷水机组传感器故障检测及效率分析[J]. 化工学报, 2015, 66(5):1815-1820.LI G N, HU Y P, CHEN H X, et al. SVDD-based chiller sensor fault detection method and its detection efficiency[J]. CIESC Journal, 2015, 66(5):1815-1820.
[18]	LI G N, HU Y P, CHEN H X, et al. An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm[J]. Energy and Buildings, 2016, 116:104-113.
[19]	ZHAO Y, WANG S W, XIAO F. Pattern recognition-based chillers fault detection method using support vector data description (SVDD)[J]. Applied Energy, 2013, 112:1041-1048.
[20]	LI G N, HU Y P, CHEN H X, et al. A sensor fault detection and diagnosis strategy for screw chiller system using support vector data description-based D-statistic and DV-contribution plots[J]. Energy and Buildings, 2016, 133:230-245.
[21]	XIAO F, ZHENG C Y, WANG S W. A fault detection and diagnosis strategy with enhanced sensitivity for centrifugal chillers[J]. Applied Thermal Engineering, 2011, 31(17/18):3963-3970.
[22]	XIAO F, ZHAO Y, WEN J, et al. Bayesian network based FDD strategy for variable air volume terminals[J]. Automation in Construction, 2014, 41:106-118.
[23]	ZHAO Y, WEN J, WANG S W. Diagnostic Bayesian networks for diagnosing air handling units faults(Ⅱ):Faults in coils and sensors[J]. Applied Thermal Engineering, 2015, 90:145-157.
[24]	ZHAO Y, XIAO F, WANG S. An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network[J]. Energy and Buildings, 2013, 57:278-288.
[25]	SHARIFI R, LANGARI R. Sensor fault diagnosis with a probabilistic decision process[J]. Mechanical Systems and Signal Processing, 2013, 34(1/2):146-155.
[26]	ROSSI T M, AUN J E. A statistical, rule-based fault detection and diagnostic method for vapor compression air conditioners[J]. HVAC&R Research, 1997, 3(1):19-37.
[27]	ZHAO Y, WANG S W, XIAO F. A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression[J]. Applied Thermal Engineering, 2013, 51(1/2):560-572.
[28]	WANG Z, WANG Z, HE S, et al. Fault detection and diagnosis of chillers using Bayesian network merged distance rejection and multi-source non-sensor information[J]. Applied Energy, 2017, 188:200-214.
[29]	胡云鹏, 陈焕新, 周诚, 等. 基于主元分析法的冷水机组传感器故障检测效率分析[J]. 化工学报, 2012, 63(S2):85-88.HU T P, CHEN H X, ZHOU C, et al. Analysis of sensor fault detection in chiller based on PCA method[J]. CIESC Journal, 2012, 63(S2):85-88.
[30]	JACKSON J E. A User's Guide to Principal Components[M]. New York:John Wiley & Sons, Inc., 1991:569.
[31]	胡云鹏. 基于主元分析的冷水机组传感器故障检测效率研究[D]. 武汉:华中科技大学, 2013.HU Y P. Study on the PCA-based sensor fault detection efficiency of the water-cooled chiller[D]. Wuhan:Huazhong University of Science and Technology, 2013.